Wentai Wu
Papers
2
Total Citations
70
H-Index
2
About
Wentai Wu is a leading researcher in time-series anomaly detection, with a focus on developing robust, unsupervised methods for real-world, event-sensitive applications. His work directly addresses critical challenges in robotic system monitoring, smart sensor networks, and data center security. Wu’s major contribution is the creation of a pioneering unsupervised, real-time anomaly detection scheme for time series with multi-seasonality, a breakthrough detailed in his most-cited paper (2020, 66 citations). This work overcomes the limitations of traditional models that struggle with diverse data sources and varying seasonal patterns. He further advanced the field with his “Local Trend Inconsistency” approach (2019), a prediction-driven framework that enhances detection accuracy by analyzing local trend deviations. By tackling the complexity of multi-seasonal data without requiring labeled training sets, Wu’s research provides scalable, practical solutions for automated monitoring systems. His innovative algorithms have significant implications for improving the reliability and security of autonomous systems and IoT infrastructures, making him a notable contributor to the intersection of machine learning and real-time analytics.
Research Focus
Key Achievements
Top Papers
- 1
- 2